Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1773 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.1298. Min Act: -0.0001

Data Index: 1202278 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0840. Min Act: -0.0001

Data Index: 731486 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1210706 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0855. Min Act: -0.0001

Data Index: 956400 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0320. Min Act: -0.0001

Data Index: 192863 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0813. Min Act: -0.0001

Data Index: 509719 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0424. Min Act: -0.0001

Data Index: 876746 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9123. Min Act: -0.0001

Data Index: 686886 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0386. Min Act: -0.0001

Data Index: 1054264 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 1.1751. Min Range: -1.1751

Max Act: 1.0007. Min Act: -0.0001

Data Index: 127826 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8820. Min Act: -0.0001

Data Index: 1064857 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9776. Min Act: -0.0001

Data Index: 566386 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1095897 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9346. Min Act: -0.0001

Data Index: 541671 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.9089. Min Act: -0.0001

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8117. Min Act: -0.0001

Data Index: 1285668 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8557. Min Act: -0.0001

Data Index: 117513 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8987. Min Act: -0.0001

Data Index: 55927 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.8158. Min Act: -0.0001

Data Index: 934975 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.1751. Min Range: -1.1751

Max Act: 0.7894. Min Act: -0.0001

Data Index: 595225 (C4 (Web Text))

Max Activating Token Index: 712